Upload app.py

app.py

@@ -0,0 +1,265 @@
+"""
+Main Gradio application interface for AudioDubb
+Provides web UI for audio dubbing on Hugging Face Spaces
+"""
+
+import logging
+import gradio as gr
+import os
+import tempfile
+from typing import Optional, Tuple, Union
+from pathlib import Path
+from src.core.pipeline import DubbingPipeline
+from src.core.audio_processor import AudioProcessor
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+# Initialize pipeline
+pipeline = DubbingPipeline()
+audio_processor = AudioProcessor()
+
+# Disclaimer text
+DISCLAIMER = """
+⚠️ **IMPORTANT DISCLAIMER** ⚠️
+
+AudioDubb is designed for **educational and personal use only**. 
+
+**Please use responsibly:**
+- Do not use this tool to create misleading or deceptive content
+- Do not impersonate individuals without their explicit consent
+- Respect intellectual property rights and privacy
+- Follow all applicable laws and regulations in your jurisdiction
+
+**Privacy Notice:**
+- All audio files are processed in-memory only
+- No audio files, transcriptions, or data are stored or logged
+- All temporary files are deleted immediately after processing
+- Your data is never transmitted to external servers beyond necessary model APIs
+
+By using AudioDubb, you agree to use it responsibly and ethically.
+"""
+
+
+def process_audio(
+    input_audio: Union[str, Tuple],
+    target_language: str,
+    source_language: Optional[str] = None,
+    speed: float = 1.0,
+    emotion: str = "neutral"
+) -> Tuple[Optional[str], str]:
+    """
+    Main processing function for the Gradio interface
+    
+    Args:
+        input_audio: Uploaded audio file (path or tuple from Gradio)
+        target_language: Target language for dubbing
+        source_language: Source language (optional, auto-detected)
+        speed: Speech speed multiplier
+        emotion: Emotion to apply
+    
+    Returns:
+        Tuple of (output_audio_path, status_message)
+    """
+    temp_files_to_cleanup = []
+    
+    try:
+        # Handle Gradio audio input (can be tuple or file path)
+        if isinstance(input_audio, tuple):
+            sample_rate, audio_data = input_audio
+            temp_input = audio_processor.create_temp_audio_file()
+            temp_files_to_cleanup.append(temp_input)
+            audio_processor.save_audio(audio_data, sample_rate, temp_input)
+            input_audio_path = temp_input
+        else:
+            input_audio_path = input_audio
+        
+        logger.info(f"Processing audio with target language: {target_language}")
+        
+        # Validate audio file
+        if not audio_processor.validate_audio_file(input_audio_path):
+            return None, "❌ Unsupported audio format. Please use WAV, MP3, M4A, FLAC, or OGG."
+        
+        # Process through pipeline
+        output_path, metadata = pipeline.dub_audio(
+            input_audio_path=input_audio_path,
+            target_language=target_language,
+            source_language=source_language,
+            speed=speed,
+            emotion=emotion
+        )
+        
+        # Build success message
+        status_msg = f"""
+✅ **Dubbing Complete!**
+
+**Source Details:**
+- Original Language: {metadata['stages']['transcription']['source_language']}
+- Duration: {metadata['output_duration_seconds']:.2f} seconds
+
+**Translation:**
+- Target Language: {metadata['stages']['translation']['target_language']}
+
+**Output:**
+- Download your dubbed audio below
+- Quality: High-fidelity voice cloning with emotion preservation
+"""
+        
+        logger.info("Audio processing completed successfully")
+        return output_path, status_msg
+        
+    except Exception as e:
+        error_msg = f"❌ **Error Processing Audio**: {str(e)}\n\nPlease check your audio file and try again."
+        logger.error(f"Error in process_audio: {str(e)}")
+        return None, error_msg
+    
+    finally:
+        # Cleanup temporary files
+        for temp_file in temp_files_to_cleanup:
+            audio_processor.cleanup_temp_file(temp_file)
+
+
+def get_supported_languages():
+    """Get supported languages for the interface"""
+    supported = pipeline.get_supported_languages()
+    return supported["languages"]
+
+
+def create_interface():
+    """Create and return the Gradio interface"""
+    
+    supported_langs = get_supported_languages()
+    
+    with gr.Blocks(theme=gr.themes.Soft(), title="AudioDubb - Multilingual Audio Dubbing") as demo:
+        
+        # Header
+        gr.Markdown("""
+# 🎙️ AudioDubb
+## AI-Powered Multilingual Audio Dubbing
+
+Transform your audio into any language while preserving the original speaker's voice, emotion, and natural expression.
+""")
+        
+        # Disclaimer
+        gr.Markdown(DISCLAIMER)
+        
+        # Main content
+        with gr.Row():
+            with gr.Column(scale=1):
+                gr.Markdown("### Input")
+                
+                # Audio upload
+                input_audio = gr.Audio(
+                    label="Upload Audio File",
+                    sources=["upload", "microphone"]
+                )
+                
+                # Language selection
+                target_language = gr.Dropdown(
+                    choices=supported_langs,
+                    value="english",
+                    label="Target Language",
+                    interactive=True
+                )
+                
+                # Advanced options
+                with gr.Accordion("Advanced Options", open=False):
+                    source_language = gr.Dropdown(
+                        choices=["Auto-Detect"] + supported_langs,
+                        value="Auto-Detect",
+                        label="Source Language",
+                        interactive=True
+                    )
+                    
+                    speed = gr.Slider(
+                        minimum=0.5,
+                        maximum=2.0,
+                        value=1.0,
+                        step=0.1,
+                        label="Speech Speed"
+                    )
+                    
+                    emotion = gr.Dropdown(
+                        choices=["neutral", "happy", "sad", "angry", "surprised", "excited"],
+                        value="neutral",
+                        label="Emotion"
+                    )
+                
+                # Process button
+                process_btn = gr.Button(
+                    "🎬 Start Dubbing",
+                    variant="primary",
+                    scale=1
+                )
+            
+            with gr.Column(scale=1):
+                gr.Markdown("### Output")
+                
+                # Status message
+                status_msg = gr.Markdown(
+                    "Upload an audio file and select a target language to begin."
+                )
+                
+                # Output audio
+                output_audio = gr.Audio(
+                    label="Dubbed Audio"
+                )
+                
+                # Download button (implicit in output_audio)
+                gr.Markdown(
+                    "Right-click the audio player to download, or use the download button in the audio widget."
+                )
+        
+        # Examples
+        gr.Markdown("### Examples")
+        gr.Markdown(
+            "Upload an audio file and select a target language to begin dubbing."
+        )
+        
+        # Connect process button
+        process_btn.click(
+            fn=lambda audio, target_lang, src_lang, spd, emo: process_audio(
+                audio,
+                target_lang,
+                src_lang if src_lang != "Auto-Detect" else None,
+                spd,
+                emo
+            ),
+            inputs=[input_audio, target_language, source_language, speed, emotion],
+            outputs=[output_audio, status_msg]
+        )
+        
+        # Footer
+        gr.Markdown("""
+---
+**AudioDubb** | AI-Powered Multilingual Dubbing Engine
+- Built for Hugging Face Spaces
+- Supports 20+ languages
+- Privacy-first: No data storage or logging
+- Educational and personal use only
+""")
+    
+    return demo
+
+
+if __name__ == "__main__":
+    try:
+        # Create and launch interface
+        demo = create_interface()
+        
+        # Launch with configuration for Hugging Face Spaces ONLY
+        # This application runs EXCLUSIVELY on Hugging Face Spaces
+        # All processing is cloud-based with no local storage
+        demo.launch(
+            server_name="0.0.0.0",
+            server_port=7860,
+            share=False,
+            show_error=True,
+            show_api=False,
+            max_threads=10
+        )
+    except Exception as e:
+        logger.error(f"Failed to launch interface: {str(e)}")
+        raise